© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 56106
    Prev
    Next
    INDEX
    Explanations

    terms related to decentralization and centralization in systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arten
    -0.09
    okud
    -0.08
    raq
    -0.08
    inium
    -0.07
    arseille
    -0.07
     crossorigin
    -0.07
    .joda
    -0.07
    кÑĥл
    -0.07
    -dropdown
    -0.07
    INAL
    -0.07
    POSITIVE LOGITS
    ism
    0.08
    ised
    0.07
    avel
    0.06
    um
    0.06
    al
    0.06
    ize
    0.06
    /local
    0.06
    a
    0.06
     freak
    0.06
     structure
    0.06
    Activations Density 0.002%

    No Known Activations